In this paper, a new continuous probability distribution has been proposed. The proposed distribution is considered as one of the extended distributions of Rayleigh distribution, which is well known in probability Theory and its applications. The distribution under consideration is titled "Exponential Log-compound Rayleigh distribution". proposed. The statistical properties of distribution parameters estimating using Maximum likelihood technique and Fisher information matrix are investigated theoretically. The evaluating of distribution performance is demonstrated on both simulated data and real data. Based on the values of bias, MSE and Fisher information matrix of the parameters estimates, the proposed distribution is considered to be working well.

Rotating machinery is a critical component in mechanical systems, widely used across industrial applications. Due to time-varying speed conditions and complex operating environments, it is highly prone to various failures. Without timely diagnosis and maintenance, such failures can lead to significant performance degradation or catastrophic outcomes. To address the challenges posed by non-stationary operating conditions and vibration signals, researchers have developed diverse fault diagnosis methods, including advanced non-stationary signal processing techniques and data-driven approaches. Among these, generalized demodulation (GD) has demonstrated particular effectiveness in extracting fault-related features from complex signals. This paper provides a comprehensive review of GD-based fault diagnosis methods for rotating machinery. It revisits the fundamental concepts and theoretical basis of GD, analyzes the limitations of traditional approaches, and systematically compares GD with other widely used methods. Furthermore, existing GD-based techniques are categorized into speed-dependent and speed-independent methods based on their reliance on rotational speed, with representative studies and applications discussed. Finally, future research directions and current challenges in GD-based diagnosis are outlined, offering valuable insights for researchers and practitioners in the field.

Planetary gear systems in industrial equipment, characterized by highly integrated structures, non-stationary operating conditions, and heavy-load characteristics, result in significant attenuation of fault-related vibration features, severely limiting the effectiveness of fault diagnosis. Traditional studies often use periodic modulation terms, such as the Hanning window function, to approximate the spatiotemporal distribution characteristics of meshing forces. Although these methods can effectively extract global vibration features of healthy gears (such as meshing frequency and its harmonics), they have significant limitations and are unable to analyze the nonlinear diffusion process of fault impacts through complex paths, resulting in distortion in the phase delay and amplitude attenuation patterns of fault impacts. To address these issues, this study investigates the vibration transmission characteristics of a planetary gearbox through rigid-flexible coupling simulation analysis, focusing on the transmission delay effects of impact responses to the vibration sensors at different housing locations. The study qualitatively clarifies the intrinsic relationship between transmission delay characteristics of the gear-sensor spatial relationship, providing a theoretical foundation for accurate analysis of vibration signals in planetary gear sets. The research highlights the significant spatiotemporal characteristics of the vibration responses when the fault collisions occur at different locations during the rotation and revolution of planet gears.

Early and precise diagnosis of brain tumors is essential for successful treatment planning and improved patient outcomes. This paper introduces a novel hybrid deep model that incorporates DenseNet121, a convolutional neural network (CNN), and the Swin Transformer, a vision transformer model, by feature-level fusion to classify brain tumors from magnetic resonance imaging (MRI) scans. The suggested method provides a more discriminative and better representation by uniting the global context capability of the Transformer model with the local feature extraction capability of the CNN model. The suggested method was trained and assessed on a publicly available brain MRI dataset of four classes: glioma, meningioma, pituitary tumor, and no tumor. Experimental results indicate that the proposed approach outperforms many baseline models including VGG16, MobileNetV2, and AlexNet with an accuracy of 99.39%, precision of 99.36%, recall of 99.34%, and F1-score of 99.35%. Grad-CAM was utilized to visualize class-discriminative regions in the MRI scans to enhance interpretability, hence validating the model's emphasis on tumor-relevant regions. These outcomes prove the efficacy of coupling Transformer and CNN architectures in obtaining accurate and interpretable brain tumor classification from MRI scans.

 Fuzzy Neural Networks (FNNs) enhance conventional Artificial Neural Networks (ANNs) by incorporating fuzzy membership functions, which enable the handling of uncertainty, ambiguity, and imprecise information. While Fuzzy Backpropagation Neural Networks (FBNNs) improve classification performance across noisy datasets, the effectiveness of fuzzification heavily depends on the proper tuning of membership function parameters—typically optimized manually. This paper presents a novel Artificial Immune System framework for optimizing Fuzzy Backpropagation Neural Networks used in the classification of biological image data. The approach integrates a fuzzy min–max fuzzification layer with a feed-forward backpropagation network and applies an optimization version of an Artificial Immune Network model, derived from opt-aiNet, to tune trapezoidal membership functions. Experimental results confirm that the proposed immune-driven optimization is an effective technique for enhancing FBNN robustness and generalization.